摘要
在对常规函数链接型神经网络(FLANN)构造方法认识的基础上,研究了一种基于最小二乘支持向量机(LS-SVM)构造FLANN的新方法,并利用该方法对非线性对象模型及逆模型进行建立.将该方法的非线性系统辨识技术应用于自适应逆控制中,提高非线性系统的自适应性,改善动态特性.设计出了一种自适应逆控制系统,不仅可以得到较好的动态响应,还能使扰动减小到最小.
With the recognition of the construction method of generic functional link artificial neural network(FLANN),a novel construction method based on least squares support vector machine(LS-SVM)is discussed and applied to the method of nonlinear object model and inverse model building.The method of nonlinear system identification technology is applied to the adaptive inverse control to increase the self-adaptive nonlinear system and improve the dynamic properties.The self-adaptive inverse control system can not only get a better dynamic response but also reduce the noise and disturbance to a minimum.
出处
《兰州交通大学学报》
CAS
2010年第6期70-73,共4页
Journal of Lanzhou Jiaotong University
关键词
函数链接型神经网络
最小二乘支持向量机
自适应逆控制
functional link artificial neural network(FLANN)
least squares support vector machine(LS-SVM)
adaptive inverse control